#include "tree.h"
#include "commit.h"
#include "tag.h"
-#include "diff.h"
-#include "revision.h"
+#include "tree-walk.h"
#include "builtin.h"
#include <regex.h>
+#include <fnmatch.h>
-static int pathspec_matches(struct diff_options *opt, const char *name)
+/*
+ * git grep pathspecs are somewhat different from diff-tree pathspecs;
+ * pathname wildcards are allowed.
+ */
+static int pathspec_matches(const char **paths, const char *name)
{
- int i, j;
- int namelen;
- if (!opt->nr_paths)
+ int namelen, i;
+ if (!paths || !*paths)
return 1;
namelen = strlen(name);
- for (i = 0; i < opt->nr_paths; i++) {
- const char *match = opt->paths[i];
- int matchlen = opt->pathlens[i];
- if (matchlen <= namelen) {
- if (!strncmp(name, match, matchlen))
+ for (i = 0; paths[i]; i++) {
+ const char *match = paths[i];
+ int matchlen = strlen(match);
+ const char *cp, *meta;
+
+ if ((matchlen <= namelen) &&
+ !strncmp(name, match, matchlen) &&
+ (match[matchlen-1] == '/' ||
+ name[matchlen] == '\0' || name[matchlen] == '/'))
+ return 1;
+ if (!fnmatch(match, name, 0))
+ return 1;
+ if (name[namelen-1] != '/')
+ continue;
+
+ /* We are being asked if the directory ("name") is worth
+ * descending into.
+ *
+ * Find the longest leading directory name that does
+ * not have metacharacter in the pathspec; the name
+ * we are looking at must overlap with that directory.
+ */
+ for (cp = match, meta = NULL; cp - match < matchlen; cp++) {
+ char ch = *cp;
+ if (ch == '*' || ch == '[' || ch == '?') {
+ meta = cp;
+ break;
+ }
+ }
+ if (!meta)
+ meta = cp; /* fully literal */
+
+ if (namelen <= meta - match) {
+ /* Looking at "Documentation/" and
+ * the pattern says "Documentation/howto/", or
+ * "Documentation/diff*.txt". The name we
+ * have should match prefix.
+ */
+ if (!memcmp(match, name, namelen))
return 1;
continue;
}
- /* If name is "Documentation" and pathspec is
- * "Documentation/", they should match. Maybe
- * we would want to strip it in get_pathspec()???
- */
- if (strncmp(name, match, namelen))
+
+ if (meta - match < namelen) {
+ /* Looking at "Documentation/howto/" and
+ * the pattern says "Documentation/h*";
+ * match up to "Do.../h"; this avoids descending
+ * into "Documentation/technical/".
+ */
+ if (!memcmp(match, name, meta - match))
+ return 1;
continue;
- for (j = namelen; j < matchlen; j++)
- if (match[j] != '/')
- break;
- if (matchlen <= j)
- return 1;
+ }
}
return 0;
}
-struct grep_opt {
+struct grep_pat {
+ struct grep_pat *next;
+ const char *origin;
+ int no;
const char *pattern;
regex_t regexp;
+};
+
+struct grep_opt {
+ struct grep_pat *pattern_list;
+ struct grep_pat **pattern_tail;
+ regex_t regexp;
unsigned linenum:1;
unsigned invert:1;
+ unsigned name_only:1;
+ unsigned unmatch_name_only:1;
+ unsigned count:1;
+ unsigned word_regexp:1;
+ unsigned fixed:1;
+#define GREP_BINARY_DEFAULT 0
+#define GREP_BINARY_NOMATCH 1
+#define GREP_BINARY_TEXT 2
+ unsigned binary:2;
int regflags;
unsigned pre_context;
unsigned post_context;
};
+static void add_pattern(struct grep_opt *opt, const char *pat,
+ const char *origin, int no)
+{
+ struct grep_pat *p = xcalloc(1, sizeof(*p));
+ p->pattern = pat;
+ p->origin = origin;
+ p->no = no;
+ *opt->pattern_tail = p;
+ opt->pattern_tail = &p->next;
+ p->next = NULL;
+}
+
+static void compile_patterns(struct grep_opt *opt)
+{
+ struct grep_pat *p;
+ for (p = opt->pattern_list; p; p = p->next) {
+ int err = regcomp(&p->regexp, p->pattern, opt->regflags);
+ if (err) {
+ char errbuf[1024];
+ char where[1024];
+ if (p->no)
+ sprintf(where, "In '%s' at %d, ",
+ p->origin, p->no);
+ else if (p->origin)
+ sprintf(where, "%s, ", p->origin);
+ else
+ where[0] = 0;
+ regerror(err, &p->regexp, errbuf, 1024);
+ regfree(&p->regexp);
+ die("%s'%s': %s", where, p->pattern, errbuf);
+ }
+ }
+}
+
static char *end_of_line(char *cp, unsigned long *left)
{
unsigned long l = *left;
return cp;
}
+static int word_char(char ch)
+{
+ return isalnum(ch) || ch == '_';
+}
+
static void show_line(struct grep_opt *opt, const char *bol, const char *eol,
const char *name, unsigned lno, char sign)
{
printf("%s%c", name, sign);
if (opt->linenum)
printf("%d%c", lno, sign);
- printf("%.*s\n", eol-bol, bol);
+ printf("%.*s\n", (int)(eol-bol), bol);
+}
+
+/*
+ * NEEDSWORK: share code with diff.c
+ */
+#define FIRST_FEW_BYTES 8000
+static int buffer_is_binary(const char *ptr, unsigned long size)
+{
+ if (FIRST_FEW_BYTES < size)
+ size = FIRST_FEW_BYTES;
+ if (memchr(ptr, 0, size))
+ return 1;
+ return 0;
+}
+
+static int fixmatch(const char *pattern, char *line, regmatch_t *match)
+{
+ char *hit = strstr(line, pattern);
+ if (!hit) {
+ match->rm_so = match->rm_eo = -1;
+ return REG_NOMATCH;
+ }
+ else {
+ match->rm_so = hit - line;
+ match->rm_eo = match->rm_so + strlen(pattern);
+ return 0;
+ }
}
static int grep_buffer(struct grep_opt *opt, const char *name,
} *prev = NULL, *pcl;
unsigned last_hit = 0;
unsigned last_shown = 0;
+ int binary_match_only = 0;
const char *hunk_mark = "";
+ unsigned count = 0;
+
+ if (buffer_is_binary(buf, size)) {
+ switch (opt->binary) {
+ case GREP_BINARY_DEFAULT:
+ binary_match_only = 1;
+ break;
+ case GREP_BINARY_NOMATCH:
+ return 0; /* Assume unmatch */
+ break;
+ default:
+ break;
+ }
+ }
if (opt->pre_context)
prev = xcalloc(opt->pre_context, sizeof(*prev));
while (left) {
regmatch_t pmatch[10];
char *eol, ch;
- int hit;
+ int hit = 0;
+ struct grep_pat *p;
eol = end_of_line(bol, &left);
ch = *eol;
*eol = 0;
- hit = !regexec(&opt->regexp, bol, ARRAY_SIZE(pmatch),
- pmatch, 0);
+ for (p = opt->pattern_list; p; p = p->next) {
+ if (!opt->fixed) {
+ regex_t *exp = &p->regexp;
+ hit = !regexec(exp, bol, ARRAY_SIZE(pmatch),
+ pmatch, 0);
+ }
+ else {
+ hit = !fixmatch(p->pattern, bol, pmatch);
+ }
+
+ if (hit && opt->word_regexp) {
+ /* Match beginning must be either
+ * beginning of the line, or at word
+ * boundary (i.e. the last char must
+ * not be alnum or underscore).
+ */
+ if ((pmatch[0].rm_so < 0) ||
+ (eol - bol) <= pmatch[0].rm_so ||
+ (pmatch[0].rm_eo < 0) ||
+ (eol - bol) < pmatch[0].rm_eo)
+ die("regexp returned nonsense");
+ if (pmatch[0].rm_so != 0 &&
+ word_char(bol[pmatch[0].rm_so-1]))
+ hit = 0;
+ if (pmatch[0].rm_eo != (eol-bol) &&
+ word_char(bol[pmatch[0].rm_eo]))
+ hit = 0;
+ }
+ if (hit)
+ break;
+ }
+ /* "grep -v -e foo -e bla" should list lines
+ * that do not have either, so inversion should
+ * be done outside.
+ */
if (opt->invert)
hit = !hit;
+ if (opt->unmatch_name_only) {
+ if (hit)
+ return 0;
+ goto next_line;
+ }
if (hit) {
+ count++;
+ if (binary_match_only) {
+ printf("Binary file %s matches\n", name);
+ return 1;
+ }
+ if (opt->name_only) {
+ printf("%s\n", name);
+ return 1;
+ }
/* Hit at this line. If we haven't shown the
* pre-context lines, we would need to show them.
+ * When asked to do "count", this still show
+ * the context which is nonsense, but the user
+ * deserves to get that ;-).
*/
if (opt->pre_context) {
unsigned from;
}
if (last_shown && lno != last_shown + 1)
printf(hunk_mark);
- show_line(opt, bol, eol, name, lno, ':');
+ if (!opt->count)
+ show_line(opt, bol, eol, name, lno, ':');
last_shown = last_hit = lno;
}
else if (last_hit &&
prev->bol = bol;
prev->eol = eol;
}
+
+ next_line:
*eol = ch;
bol = eol + 1;
+ if (!left)
+ break;
left--;
lno++;
}
+
+ if (opt->unmatch_name_only) {
+ /* We did not see any hit, so we want to show this */
+ printf("%s\n", name);
+ return 1;
+ }
+
+ /* NEEDSWORK:
+ * The real "grep -c foo *.c" gives many "bar.c:0" lines,
+ * which feels mostly useless but sometimes useful. Maybe
+ * make it another option? For now suppress them.
+ */
+ if (opt->count && count)
+ printf("%s:%u\n", name, count);
return !!last_hit;
}
return i;
}
-static int grep_cache(struct grep_opt *opt, struct rev_info *revs, int cached)
+static int grep_cache(struct grep_opt *opt, const char **paths, int cached)
{
int hit = 0;
int nr;
struct cache_entry *ce = active_cache[nr];
if (ce_stage(ce) || !S_ISREG(ntohl(ce->ce_mode)))
continue;
- if (!pathspec_matches(&revs->diffopt, ce->name))
+ if (!pathspec_matches(paths, ce->name))
continue;
if (cached)
hit |= grep_sha1(opt, ce->sha1, ce->name);
return hit;
}
-static int grep_tree(struct grep_opt *opt, struct rev_info *revs,
+static int grep_tree(struct grep_opt *opt, const char **paths,
struct tree_desc *tree,
const char *tree_name, const char *base)
{
int hit = 0;
const char *path;
const unsigned char *sha1;
- char *down_base;
+ char *down;
char *path_buf = xmalloc(PATH_MAX + strlen(tree_name) + 100);
if (tree_name[0]) {
int offset = sprintf(path_buf, "%s:", tree_name);
- down_base = path_buf + offset;
- strcat(down_base, base);
+ down = path_buf + offset;
+ strcat(down, base);
}
else {
- down_base = path_buf;
- strcpy(down_base, base);
+ down = path_buf;
+ strcpy(down, base);
}
len = strlen(path_buf);
pathlen = strlen(path);
strcpy(path_buf + len, path);
- if (!pathspec_matches(&revs->diffopt, down_base))
+ if (S_ISDIR(mode))
+ /* Match "abc/" against pathspec to
+ * decide if we want to descend into "abc"
+ * directory.
+ */
+ strcpy(path_buf + len + pathlen, "/");
+
+ if (!pathspec_matches(paths, down))
;
else if (S_ISREG(mode))
hit |= grep_sha1(opt, sha1, path_buf);
if (!data)
die("unable to read tree (%s)",
sha1_to_hex(sha1));
- strcpy(path_buf + len + pathlen, "/");
sub.buf = data;
- hit = grep_tree(opt, revs, &sub, tree_name, down_base);
+ hit |= grep_tree(opt, paths, &sub, tree_name, down);
free(data);
}
update_tree_entry(tree);
return hit;
}
-static int grep_object(struct grep_opt *opt, struct rev_info *revs,
+static int grep_object(struct grep_opt *opt, const char **paths,
struct object *obj, const char *name)
{
if (!strcmp(obj->type, blob_type))
if (!data)
die("unable to read tree (%s)", sha1_to_hex(obj->sha1));
tree.buf = data;
- hit = grep_tree(opt, revs, &tree, name, "");
+ hit = grep_tree(opt, paths, &tree, name, "");
free(data);
return hit;
}
int cmd_grep(int argc, const char **argv, char **envp)
{
- struct rev_info rev;
- const char **dst, **src;
- int err;
int hit = 0;
- int no_more_arg = 0;
- int seen_range = 0;
- int seen_noncommit = 0;
int cached = 0;
+ int seen_dashdash = 0;
struct grep_opt opt;
- struct object_list *list;
+ struct object_list *list, **tail, *object_list = NULL;
+ const char *prefix = setup_git_directory();
+ const char **paths = NULL;
+ int i;
memset(&opt, 0, sizeof(opt));
+ opt.pattern_tail = &opt.pattern_list;
opt.regflags = REG_NEWLINE;
/*
- * Interpret and remove the grep options upfront. Sigh...
+ * If there is no -- then the paths must exist in the working
+ * tree. If there is no explicit pattern specified with -e or
+ * -f, we take the first unrecognized non option to be the
+ * pattern, but then what follows it must be zero or more
+ * valid refs up to the -- (if exists), and then existing
+ * paths. If there is an explicit pattern, then the first
+ * unrecocnized non option is the beginning of the refs list
+ * that continues up to the -- (if exists), and then paths.
*/
- for (dst = src = &argv[1]; src < argc + argv; ) {
- const char *arg = *src++;
- if (!no_more_arg) {
- if (!strcmp("--", arg)) {
- no_more_arg = 1;
- *dst++ = arg;
- continue;
- }
- if (!strcmp("--cached", arg)) {
- cached = 1;
- continue;
- }
- if (!strcmp("-i", arg) ||
- !strcmp("--ignore-case", arg)) {
- opt.regflags |= REG_ICASE;
- continue;
- }
- if (!strcmp("-v", arg) ||
- !strcmp("--invert-match", arg)) {
- opt.invert = 1;
- continue;
- }
- if (!strcmp("-E", arg) ||
- !strcmp("--extended-regexp", arg)) {
- opt.regflags |= REG_EXTENDED;
- continue;
- }
- if (!strcmp("-G", arg) ||
- !strcmp("--basic-regexp", arg)) {
- opt.regflags &= ~REG_EXTENDED;
- continue;
- }
- if (!strcmp("-e", arg)) {
- if (src < argc + argv) {
- opt.pattern = *src++;
- continue;
+
+ tail = &object_list;
+ while (1 < argc) {
+ const char *arg = argv[1];
+ argc--; argv++;
+ if (!strcmp("--cached", arg)) {
+ cached = 1;
+ continue;
+ }
+ if (!strcmp("-a", arg) ||
+ !strcmp("--text", arg)) {
+ opt.binary = GREP_BINARY_TEXT;
+ continue;
+ }
+ if (!strcmp("-i", arg) ||
+ !strcmp("--ignore-case", arg)) {
+ opt.regflags |= REG_ICASE;
+ continue;
+ }
+ if (!strcmp("-I", arg)) {
+ opt.binary = GREP_BINARY_NOMATCH;
+ continue;
+ }
+ if (!strcmp("-v", arg) ||
+ !strcmp("--invert-match", arg)) {
+ opt.invert = 1;
+ continue;
+ }
+ if (!strcmp("-E", arg) ||
+ !strcmp("--extended-regexp", arg)) {
+ opt.regflags |= REG_EXTENDED;
+ continue;
+ }
+ if (!strcmp("-F", arg) ||
+ !strcmp("--fixed-strings", arg)) {
+ opt.fixed = 1;
+ continue;
+ }
+ if (!strcmp("-G", arg) ||
+ !strcmp("--basic-regexp", arg)) {
+ opt.regflags &= ~REG_EXTENDED;
+ continue;
+ }
+ if (!strcmp("-n", arg)) {
+ opt.linenum = 1;
+ continue;
+ }
+ if (!strcmp("-H", arg)) {
+ /* We always show the pathname, so this
+ * is a noop.
+ */
+ continue;
+ }
+ if (!strcmp("-l", arg) ||
+ !strcmp("--files-with-matches", arg)) {
+ opt.name_only = 1;
+ continue;
+ }
+ if (!strcmp("-L", arg) ||
+ !strcmp("--files-without-match", arg)) {
+ opt.unmatch_name_only = 1;
+ continue;
+ }
+ if (!strcmp("-c", arg) ||
+ !strcmp("--count", arg)) {
+ opt.count = 1;
+ continue;
+ }
+ if (!strcmp("-w", arg) ||
+ !strcmp("--word-regexp", arg)) {
+ opt.word_regexp = 1;
+ continue;
+ }
+ if (!strncmp("-A", arg, 2) ||
+ !strncmp("-B", arg, 2) ||
+ !strncmp("-C", arg, 2) ||
+ (arg[0] == '-' && '1' <= arg[1] && arg[1] <= '9')) {
+ unsigned num;
+ const char *scan;
+ switch (arg[1]) {
+ case 'A': case 'B': case 'C':
+ if (!arg[2]) {
+ if (argc <= 1)
+ usage(builtin_grep_usage);
+ scan = *++argv;
+ argc--;
}
- usage(builtin_grep_usage);
+ else
+ scan = arg + 2;
+ break;
+ default:
+ scan = arg + 1;
+ break;
}
- if (!strcmp("-n", arg)) {
- opt.linenum = 1;
- continue;
+ if (sscanf(scan, "%u", &num) != 1)
+ usage(builtin_grep_usage);
+ switch (arg[1]) {
+ case 'A':
+ opt.post_context = num;
+ break;
+ default:
+ case 'C':
+ opt.post_context = num;
+ case 'B':
+ opt.pre_context = num;
+ break;
}
- if (!strcmp("-H", arg)) {
- /* We always show the pathname, so this
- * is a noop.
- */
- continue;
+ continue;
+ }
+ if (!strcmp("-f", arg)) {
+ FILE *patterns;
+ int lno = 0;
+ char buf[1024];
+ if (argc <= 1)
+ usage(builtin_grep_usage);
+ patterns = fopen(argv[1], "r");
+ if (!patterns)
+ die("'%s': %s", argv[1], strerror(errno));
+ while (fgets(buf, sizeof(buf), patterns)) {
+ int len = strlen(buf);
+ if (buf[len-1] == '\n')
+ buf[len-1] = 0;
+ /* ignore empty line like grep does */
+ if (!buf[0])
+ continue;
+ add_pattern(&opt, strdup(buf), argv[1], ++lno);
}
- if (!strcmp("-A", arg) ||
- !strcmp("-B", arg) ||
- !strcmp("-C", arg)) {
- unsigned num;
- if ((argc + argv <= src) ||
- sscanf(*src++, "%u", &num) != 1)
- usage(builtin_grep_usage);
- switch (arg[1]) {
- case 'A':
- opt.post_context = num;
- break;
- case 'C':
- opt.post_context = num;
- case 'B':
- opt.pre_context = num;
- break;
- }
+ fclose(patterns);
+ argv++;
+ argc--;
+ continue;
+ }
+ if (!strcmp("-e", arg)) {
+ if (1 < argc) {
+ add_pattern(&opt, argv[1], "-e option", 0);
+ argv++;
+ argc--;
continue;
}
+ usage(builtin_grep_usage);
+ }
+ if (!strcmp("--", arg))
+ break;
+ if (*arg == '-')
+ usage(builtin_grep_usage);
+
+ /* First unrecognized non-option token */
+ if (!opt.pattern_list) {
+ add_pattern(&opt, arg, "command line", 0);
+ break;
+ }
+ else {
+ /* We are looking at the first path or rev;
+ * it is found at argv[1] after leaving the
+ * loop.
+ */
+ argc++; argv--;
+ break;
}
- *dst++ = arg;
}
- if (!opt.pattern)
+
+ if (!opt.pattern_list)
die("no pattern given.");
+ if ((opt.regflags != REG_NEWLINE) && opt.fixed)
+ die("cannot mix --fixed-strings and regexp");
+ if (!opt.fixed)
+ compile_patterns(&opt);
- err = regcomp(&opt.regexp, opt.pattern, opt.regflags);
- if (err) {
- char errbuf[1024];
- regerror(err, &opt.regexp, errbuf, 1024);
- regfree(&opt.regexp);
- die("'%s': %s", opt.pattern, errbuf);
+ /* Check revs and then paths */
+ for (i = 1; i < argc; i++) {
+ const char *arg = argv[i];
+ unsigned char sha1[20];
+ /* Is it a rev? */
+ if (!get_sha1(arg, sha1)) {
+ struct object *object = parse_object(sha1);
+ struct object_list *elem;
+ if (!object)
+ die("bad object %s", arg);
+ elem = object_list_insert(object, tail);
+ elem->name = arg;
+ tail = &elem->next;
+ continue;
+ }
+ if (!strcmp(arg, "--")) {
+ i++;
+ seen_dashdash = 1;
+ }
+ break;
}
- init_revisions(&rev);
- *dst = NULL;
- argc = setup_revisions(dst - argv, argv, &rev, NULL);
+ /* The rest are paths */
+ if (!seen_dashdash) {
+ int j;
+ for (j = i; j < argc; j++)
+ verify_filename(prefix, argv[j]);
+ }
- /*
- * Do not walk "grep -e foo master next pu -- Documentation/"
- * but do walk "grep -e foo master..next -- Documentation/".
- * Ranged request mixed with a blob or tree object, like
- * "grep -e foo v1.0.0:Documentation/ master..next"
- * so detect that and complain.
- */
- for (list = rev.pending_objects; list; list = list->next) {
- struct object *real_obj;
- if (list->item->flags & UNINTERESTING)
- seen_range = 1;
- real_obj = deref_tag(list->item, NULL, 0);
- if (strcmp(real_obj->type, commit_type))
- seen_noncommit = 1;
+ if (i < argc)
+ paths = get_pathspec(prefix, argv + i);
+ else if (prefix) {
+ paths = xcalloc(2, sizeof(const char *));
+ paths[0] = prefix;
+ paths[1] = NULL;
}
- if (!rev.pending_objects)
- return !grep_cache(&opt, &rev, cached);
+
+ if (!object_list)
+ return !grep_cache(&opt, paths, cached);
+
if (cached)
- die("both --cached and revisions given.");
-
- if (seen_range && seen_noncommit)
- die("both A..B and non commit are given.");
- if (seen_range) {
- struct commit *commit;
- prepare_revision_walk(&rev);
- while ((commit = get_revision(&rev)) != NULL) {
- unsigned char *sha1 = commit->object.sha1;
- const char *n = find_unique_abbrev(sha1, rev.abbrev);
- char rev_name[41];
- strcpy(rev_name, n);
- if (grep_object(&opt, &rev, &commit->object, rev_name))
- hit = 1;
- commit->buffer = NULL;
- }
- return !hit;
- }
+ die("both --cached and trees are given.");
- /* all of them are non-commit; do not walk, and
- * do not lose their names.
- */
- for (list = rev.pending_objects; list; list = list->next) {
+ for (list = object_list; list; list = list->next) {
struct object *real_obj;
real_obj = deref_tag(list->item, NULL, 0);
- if (grep_object(&opt, &rev, real_obj, list->name))
+ if (grep_object(&opt, paths, real_obj, list->name))
hit = 1;
}
return !hit;